© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25221
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the Go pointer/address operators (the “*” and related “&”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amide
    -0.07
    іти
    -0.07
     itemView
    -0.07
    Clin
    -0.07
    aths
    -0.06
     chlor
    -0.06
     Page
    -0.06
     TYPE
    -0.06
    Find
    -0.06
    preg
    -0.06
    POSITIVE LOGITS
    )");↵↵
    0.07
    QUIRES
    0.06
     verbess
    0.06
     inherited
    0.06
     doma
    0.06
     英
    0.06
    !");↵
    0.06
    acic
    0.06
    ц
    0.06
    ";
    0.06
    Activations Density 0.004%

    No Known Activations